Metapaths guided Neighbors aggregated Network for?Heterogeneous Graph Reasoning
This addresses the challenge of learning from diverse real-world graph data for applications like recommendation systems, though it appears incremental in combining existing techniques.
The authors tackled the problem of heterogeneous graph embedding by proposing MHN, a method that incorporates node attributes, local/global information, and multiple metapaths, achieving better performance than state-of-the-art baselines on node classification, link prediction, and an online A/B test.
Most real-world datasets are inherently heterogeneous graphs, which involve a diversity of node and relation types. Heterogeneous graph embedding is to learn the structure and semantic information from the graph, and then embed it into the low-dimensional node representation. Existing methods usually capture the composite relation of a heterogeneous graph by defining metapath, which represent a semantic of the graph. However, these methods either ignore node attributes, or discard the local and global information of the graph, or only consider one metapath. To address these limitations, we propose a Metapaths-guided Neighbors-aggregated Heterogeneous Graph Neural Network(MHN) to improve performance. Specially, MHN employs node base embedding to encapsulate node attributes, BFS and DFS neighbors aggregation within a metapath to capture local and global information, and metapaths aggregation to combine different semantics of the heterogeneous graph. We conduct extensive experiments for the proposed MHN on three real-world heterogeneous graph datasets, including node classification, link prediction and online A/B test on Alibaba mobile application. Results demonstrate that MHN performs better than other state-of-the-art baselines.